How it thinks
Not a folder of files.
A memory that understands.
Ask the way you think, in any language you like. Second Brain finds what you meant, even when you wrote it in other words. Try it on this small sample Brain of 29 notes.
Finds a note only if it contains the very words you typed, spelled the same way.
Compares what the question means with what each note means.
A simulation in this page: nothing is sent. The sample Brain uses a small hand-made map of ideas. In the app, every note and every page of your documents gets a real meaning vector from an embeddings model, and a hit counts from a score of 0.25.
One capture, end to end
What happens between “add this” and the receipt
Speak, drop a PDF, send a web page or a photo. The Archivist reads it, understands it, files it, indexes it twice and links it to what you already know. Pick something to capture and follow it through.
- Captureyou
- Readhear · extract · see
- Understandthe Archivist
- FilePARA
- Indexwords + meaning
- Linksame ideas
- ReceiptUndo
–
–
The meaning map
Notes that mean the same thing find each other
Each dot is a note, placed by what it means, not by where it was filed. Notes about the same idea drift together, across places. The dashed lines are the “same idea” links the Brain suggests; you keep them or dismiss them.
Under the hood
Three layers of knowing, in one file on your computer
Your Brain is a single SQLite database in your user folder. Every item lives there with three ways to be found, next to its original file and the history of every change.
Words
A full-text index ranks notes and document pages by the words they hold (BM25). A word in the title counts four times as much as in the body. Exact names, numbers and codes are found here.
notes_fts · chunks_fts
Meaning
Every note, and every page of every document cut into pieces of about 1,200 characters, gets a vector of 1,536 numbers that captures what it means. Same idea in other words, even in another language: close vectors.
note_embeddings · source_chunks
Links
Your own links, the ones the Archivist adds when it files, and the “same idea” pairs it computes. You keep a suggestion or dismiss it, and the Brain remembers your answer.
links · note_related · related_choices
Around them: places (PARA), types and fields (a recipe has servings), tags, originals of your files,
restore points and a timeline of every change. spaces · item_types · sources · restore_points
How a question is answered
- Meaning first. The question becomes a vector; the closest notes above 0.25 come back, best first.
- Words complete it. Keyword hits not already found fill the list: an exact name is never lost.
- Documents next. For “what does the quote say?”, the same two searches run on document pieces, and the answer cites the page.
- Places when you name one. “What's in my Inbox?” lists the place itself, newest first.
Compared with a folder of text files and an AI that reads them
| A folder of text files | Second Brain GD | |
|---|---|---|
| You wrote “quartz for the island”, you search “countertop” | Not found | Found by meaning |
| Related notes | The links you typed by hand | Suggested for every note, kept or dismissed by you |
| A scanned PDF | An image nobody can search | Read page by page (local OCR), searchable, cited by page |
| Filing | You pick the folder | The Archivist files in PARA and asks when it isn't sure |
| An AI looking for an answer | Opens and reads files until it finds it | Searches with tools, reads only the few items that matter |
| An AI that writes | Edits your files directly | Proposes; the Archivist files with your rules; a receipt and Undo |
| Going back | If you set up versioning | Restore points and a timeline of every change, built in |
AI-native
The right model for each job
Second Brain is not one chatbot. Each job goes to the model that does it best: a fast one to talk, a reasoning one for the weekly review, a transcriber for your voice, an embeddings model for meaning, and your own computer for what it can do alone. Pick a way in to see the route.
You
The engine
Models
Pick a way in on the left.
Measured, not guessed
Chat with tools moved to gpt-6-sol after replaying the owner's real failures on a throwaway Brain: 12 out of 12, against 11 for gpt-4o. Filing: 10 out of 10 test captures in 1.45 s.
Never stuck
Every model is a setting. When your OpenAI project lacks one, the job falls back (to gpt-4o or gpt-4o-mini) instead of failing.
Local where it can be
PDF text, scanned pages (Windows OCR or Tesseract), keyword search, the graph and your files stay on your computer. Local AI models are on the roadmap.
Agents
An AI that searches, instead of reading everything
A Brain grows to thousands of items; no model should swallow it whole. The agents use tools, like you would use a search engine: search, open the few items that matter, cite them, act only through tools you can undo.
Archivist
Agent number one. Files, links, answers with sources, drives the app by voice. About sixty tools, every write undoable.
Sparring
Your thinking partner. Reads your Brain to question, challenge or reassure you; changes nothing, and saves a synthesis only when you approve it.
Agent Builder
Interviews you, writes a new agent's instructions and picks its tools. You see the draft; it exists when you say yes.
Over MCP
One memory for every agent you use
Claude Code, Codex or Claude Desktop plug into the Brain over MCP. They search it by meaning; what they learn comes back as proposals the Archivist files with your rules. What one agent learns, the next one knows.
- Ask. A Claude Code session in Agent Manager calls
search: “what do we know about the quote?” - Answer. The Brain searches by meaning and words, and sends three short hits with their ids.
- Propose. The session learned something; it calls
propose_item. Nothing is written yet. - File. The Archivist checks it with your rules, files it, links it, and answers with a receipt.
- Remember. Tomorrow, a Codex session asks a related question and finds it.
Each agent has its own token and level, and the Brain listens on your computer only. Levels are permissions inside the app, not network security: read the AI notice.
What it takes, honestly
- Meaning needs an OpenAI key. Without one, everything still works with words: search, filing by hand, the graph.
- What you send to a model leaves your computer. The text of a note to make its vector, your question to answer it. Your Brain itself, its files and its history stay in your user folder.
- Built for one person on one computer. It is a lab, not a server: don't put it on the internet.